MEMP PhD Thesis Defense (11:00am): Nalini Singh

Physics-Inspired Deep Learning for Inverse Problems in MRI

We demonstrate the power of combining the forward image acquisition model with deep learning solutions for inverse problems in magnetic resonance imaging (MRI), from individual network layers to the network architecture design and inference procedure.

First, we propose neural network layers that combine image space representations with representations in Fourier space, where MRI data is acquired. These layers can be used as drop-in replacements for standard image space convolutions in a variety of network architectures and yield higher quality reconstructions across a wide range of MR imaging tasks.

Next, we demonstrate a deep learning framework for MRI motion correction, where the forward imaging model informs both the network architecture and the inference procedure. Our method incorporates potentially unknown motion parameters as inputs to the network and then optimizes them for each test example. The optimization is performed via an objective function that forces the reconstructed image and estimated motion parameters to be consistent with the acquired data. This approach reduces the joint image-motion parameter search used by most motion correction strategies to an inference-time search over motion parameters alone, greatly simplifying the complexity of the optimization problem to be solved for a novel image. Our hybrid method achieves the high reconstruction fidelity characteristic of deep learning solutions while retaining the benefits of explicit model-based optimization -- in particular, the ability to reject examples where the network produces poor reconstructions. Experiments demonstrate the advantages of this combined approach over purely learning or model-based reconstruction techniques.

Thesis Supervisor:
Polina Golland, PhD
Sunlin (1966) and Priscilla Chou Professor of Electrical Engineering and Computer Science, MIT

Thesis Committee Chair:
Elfar Adalsteinsson, PhD
Eaton-Peabody Professor of Electrical Engineering and Computer Science, MIT; Professor, Institute for Medical Engineering and Science, MIT

Thesis Readers:
Bruce Rosen, MD, PhD
Laurence Lamson Robbins Professor of Radiology, Massachusetts General Hospital, HMS; Director, Athinoula A. Martinos Center for Biomedical Imaging

Robert Frost, PhD
Assistant Professor of Radiology, Massachusetts General Hospital, HMS
------------------------------------------------------------------------------------------------------

Zoom invitation –

Nalini Singh is inviting you to a scheduled Zoom meeting.

Topic: Nalini Singh Thesis Defense
Time: August 16, 2023, 11:00 AM Eastern Time (US and Canada)

Your participation is important to us: please notify hst [at] mit.edu (hst[at]mit[dot]edu), at least 3 business days in advance, if you require accommodations in order to access this event.

Join Zoom Meeting
https://mit.zoom.us/j/94894377297

Password: MRI

One tap mobile
+16465588656,,94894377297# US (New York)
+16699006833,,94894377297# US (San Jose)

Meeting ID: 948 9437 7297

US: +1 646 558 8656 or +1 669 900 6833

International Numbers: https://mit.zoom.us/u/abWGyIyfAX

Join by SIP
94894377297 [at] zoomcrc.com

Join by Skype for Business
https://mit.zoom.us/skype/94894377297
------------------------------------------------------------------------------------------------------
Directions to Star Conference Room, 32-D463

The Star Conference room is on the 4th floor of the Dreyfoos Wing in the MIT Stata Center (Building 32).

To get there: Enter Building 32 at the Vassar street entrance and proceed straight ahead; there will be elevators to the right. Take the elevators to the 4th floor; exit to the left and then turn right at the end of the elevator bank. At the end of the short corridor, turn right, just before the R&D Dining room. The Star Conference Room is straight ahead, just past a set of stairs